AR2-4FV：面向固定视角视频长期定位的锚定指代与重识别
AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos
把固定视角视频中静态背景结构蒸馏成离线锚框库，作为文本查询对齐的持久语义记忆，可在目标长时间离场后重新捕获；这种「背景即记忆」的思路可迁移到长时视频目标跟踪与语言引导定位中，缓解逐帧指代漂移与重识别不可靠的问题。
原文依据 An offline Anchor Bank is distilled from static background structures; at inference, the text query is aligned with this bank to produce an Anchor Map
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论固定视角视频中的长期语言引导指代具有挑战性：指代目标可能被遮挡或长时间离开场景后再次进入，而逐帧指代流程会因重识别（ReID）变得不可靠而发生漂移。AR2-4FV 利用背景稳定性实现长期指代。离线锚框库从静态背景结构中蒸馏得到；在推理时，文本查询与该库对齐，生成锚框图，在目标缺席时充当持久的语义记忆。基于锚框的再进入先验可在目标返回时加速重新捕获，轻量级 ReID 门控机制利用锚框帧中的位移线索维持身份连续性。该系统逐帧预测边界框，既不假设目标在第一帧中可见，也不显式建模外观变化。与最佳基线相比，AR2-4FV 的重新捕获率（RCR）提升 10.3%，重新捕获延迟（RCL）降低 24.2%，消融实验进一步证实了锚框图、再进入先验与 ReID 门控的有效性。
英文原文摘要 1096 字符
Long-term language-guided referring in fixed-view videos is challenging: the referent may be occluded or leave the scene for long intervals and later re-enter, while framewise referring pipelines drift as re-identification (ReID) becomes unreliable. AR2-4FV leverages background stability for long-term referring. An offline Anchor Bank is distilled from static background structures; at inference, the text query is aligned with this bank to produce an Anchor Map that serves as persistent semantic memory when the referent is absent. An anchor-based re-entry prior accelerates re-capture upon return, and a lightweight ReID-Gating mechanism maintains identity continuity using displacement cues in the anchor frame. The system predicts per-frame bounding boxes without assuming the target is visible in the first frame or explicitly modeling appearance variations. AR2-4FV achieves +10.3% Re-Capture Rate (RCR) improvement and -24.2% Re-Capture Latency (RCL) reduction over the best baseline, and ablation studies further confirm the benefits of the Anchor Map, re-entry prior, and ReID-Gating.